Automated Detection of Potato Plant Diseases using Machine Learning Algorithms

The agriculture industry is a crucial sector globally and plays a vital role in providing food, raw materials, and employment opportunities. However, the industry is faced with various challenges such as climate change, water scarcity, and plant diseases. Plant diseases, in particular, can cause significant damages to crop yield and quality, affecting food security and leading to economic losses. This research paper proposes an automated disease detection system for potato plants using five different machine learning algorithms, including KNN, Random Forest, CNN, Naive Bayes, and SVM and chooses the most accurate model. The system analyzes images of plant leaves to accurately classify them as healthy or diseased and even identify the specific disease affecting the plant and display results in a website. The proposed approach has the potential to provide a reliable and efficient solution for disease detection in potato plants providing higher accuracy than the previous studies in this field. it can help farmers make informed decisions and take timely action to control the spread of diseases, ultimately contributing to improving food security and the overall sustainability of the agriculture industry.